searchconsole-mcp
Provides read-only access to Google Search Console data, allowing users to query site performance metrics including keywords, clicks, impressions, CTR, rankings, and sitemap status.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@searchconsole-mcp What are my top 10 keywords by clicks this month?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
searchconsole-mcp
An MCP server that gives AI assistants read-only access to your Google Search Console data. Ask questions about your site's search performance in natural language — keywords, clicks, impressions, CTR, rankings, sitemaps, and more.
Tools
Tool | Description |
| Lists all verified Search Console properties with permission levels |
| Query keyword/page data — clicks, impressions, CTR, average position. Supports filtering by dimension, date range, search type, and pagination |
| Lists submitted sitemaps for a property |
Related MCP server: Google Search Console MCP Server
Quick Start
1. Install
git clone https://github.com/chrishart0/searchconsole-mcp.git
cd searchconsole-mcp
uv sync2. Authenticate
This server uses Google Application Default Credentials. Choose one:
Option A — Service account key (recommended for automation):
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.jsonOption B — User credentials (recommended for local development):
gcloud auth application-default login \
--scopes="https://www.googleapis.com/auth/webmasters.readonly"The service account or user must have access to the Search Console properties you want to query.
3. Connect to your MCP client
Add to ~/.claude.json:
{
"mcpServers": {
"searchconsole-mcp": {
"type": "stdio",
"command": "uv",
"args": ["run", "--directory", "/path/to/searchconsole-mcp", "searchconsole-mcp"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/key.json"
}
}
}
}Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"searchconsole-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/searchconsole-mcp", "searchconsole-mcp"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/key.json"
}
}
}
}Any MCP-compatible client can connect over stdio. Run the server with:
uv run --directory /path/to/searchconsole-mcp searchconsole-mcpExample Prompts
Once connected, try asking your AI assistant:
"What are my top 10 keywords by clicks this month?"
"Show me pages with high impressions but low CTR"
"List all my Search Console properties"
"What queries is my site ranking for on page 2 of Google?"
"Show me my sitemaps and their status"
Development
uv sync --dev
uv run pytestLicense
Available Tools
3 toolslist_sitemapsB
Lists submitted sitemaps for a Search Console property.
Args:
site_url: The site URL as it appears in Search Console
(e.g. "https://mychefai.com" or "sc-domain:mychefai.com").
Inputs: site_url (required). Returns: result
list_sitesA
Lists all verified properties in Google Search Console.
Returns site URLs and permission levels.
Inputs: no named parameters. Returns: result
query_search_analyticsA
Query Google Search Console search analytics data.
This is the main keyword research tool. Returns rows with clicks,
impressions, CTR, and average position.
Args:
site_url: The site URL as it appears in Search Console
(e.g. "https://mychefai.com" or "sc-domain:mychefai.com").
start_date: Start date in YYYY-MM-DD format.
end_date: End date in YYYY-MM-DD format.
dimensions: List of dimensions to group by. Options: query, page,
date, country, device, searchAppearance. Defaults to ["query"].
row_limit: Max rows to return (1-25000, default 1000).
start_row: Starting row offset for pagination (default 0).
dimension_filters: Optional list of filter objects. Each filter has:
- dimension: the dimension to filter on (e.g. "query", "page")
- operator: one of "contains", "equals", "notContains",
"notEquals", "includingRegex", "excludingRegex"
- expression: the filter value
Example: [{"dimension": "query", "operator": "contains",
"expression": "keto"}]
search_type: Type of search results. One of: web, image, video,
news, discover, googleNews. Default "web".
aggregation_type: How to aggregate results. One of: auto, byPage,
byProperty. If omitted, the API auto-selects.
Inputs: site_url (required), start_date (required), end_date (required), dimensions, +5 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no overlap: list_sitemaps handles sitemap management, list_sites provides property overview, and query_search_analytics focuses on search performance data. The descriptions reinforce these boundaries, making misselection unlikely.
All tools follow a consistent verb_noun pattern (list_sitemaps, list_sites, query_search_analytics) with clear, descriptive names. There are no deviations in style or convention across the set.
With only 3 tools, the set feels thin for a Search Console MCP server, lacking operations like sitemap submission/deletion, property verification, or detailed configuration management. While the tools cover core areas, the scope seems limited compared to typical API capabilities.
The tool surface has significant gaps for Search Console functionality: no create/update/delete operations for sitemaps or properties, missing tools for URL inspection, mobile usability, or security issues, and incomplete coverage of the API's core features like indexing status or rich results testing.
Maintenance
Related MCP Connectors
Google Search Console for AI assistants: traffic, rankings, indexing and page checks. Read-only.
Read-only Google Search Console and Google Analytics for AI agents.
SEO rankings and traffic from Google Search Console for AI assistants, read-only
Read-only Google Search Console, Bing, Google Analytics and privacy-friendly analytics for your AI.
Related MCP Servers
- AlicenseAqualityBmaintenanceProvides AI agents with read-only access to Google Search Console data, including search analytics, index coverage, and sitemap status. It enables users to query clicks, impressions, and ranking performance or check URL indexing status through natural language.4133 npm9MIT
- AlicenseAqualityDmaintenanceConnects Google Search Console to AI assistants, enabling natural language analysis of SEO data. Provides read-only tools for properties, search analytics, URL inspection, and sitemaps.15MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to access Google Search Console search performance and index health data, including clicks, impressions, rankings, URL inspection, and sitemap management.32 npmMIT
- AlicenseAqualityDmaintenanceEnables AI assistants to analyze Google Search Console SEO data through natural language, including search analytics, URL inspection, sitemap management, and property management.21MIT